diff options
| -rw-r--r-- | src/Text/Pandoc/Readers/DocBook.hs | 65 |
1 files changed, 37 insertions, 28 deletions
diff --git a/src/Text/Pandoc/Readers/DocBook.hs b/src/Text/Pandoc/Readers/DocBook.hs index c1d092a70..9352cd938 100644 --- a/src/Text/Pandoc/Readers/DocBook.hs +++ b/src/Text/Pandoc/Readers/DocBook.hs @@ -24,8 +24,9 @@ import Data.Text (Text) import qualified Data.Text as T import Text.HTML.TagSoup.Entity (lookupEntity) import Text.Pandoc.Builder -import Text.Pandoc.Class (PandocMonad) +import Text.Pandoc.Class (PandocMonad, report) import Text.Pandoc.Options +import Text.Pandoc.Logging (LogMessage(..)) import Text.Pandoc.Shared (crFilter, safeRead) import Text.TeXMath (readMathML, writeTeX) import Text.XML.Light @@ -690,8 +691,8 @@ parseBlock (Text (CData _ s _)) = if all isSpace s parseBlock (CRef x) = return $ plain $ str $ map toUpper x parseBlock (Elem e) = case qName (elName e) of - "toc" -> return mempty -- skip TOC, since in pandoc it's autogenerated - "index" -> return mempty -- skip index, since page numbers meaningless + "toc" -> skip -- skip TOC, since in pandoc it's autogenerated + "index" -> skip -- skip index, since page numbers meaningless "para" -> parseMixed para (elContent e) "formalpara" -> do tit <- case filterChild (named "title") e of @@ -703,9 +704,9 @@ parseBlock (Elem e) = "ackno" -> parseMixed para (elContent e) "epigraph" -> parseBlockquote "blockquote" -> parseBlockquote - "attribution" -> return mempty - "titleabbrev" -> return mempty - "authorinitials" -> return mempty + "attribution" -> skip + "titleabbrev" -> skip + "authorinitials" -> skip "bibliography" -> sect 0 "bibliodiv" -> sect 1 "biblioentry" -> parseMixed para (elContent e) @@ -745,9 +746,9 @@ parseBlock (Elem e) = <$> getBlocks e "warning" -> blockQuote . (para (strong $ str "Warning") <>) <$> getBlocks e - "area" -> return mempty - "areaset" -> return mempty - "areaspec" -> return mempty + "area" -> skip + "areaset" -> skip + "areaspec" -> skip "qandadiv" -> gets dbSectionLevel >>= sect . (+1) "question" -> addToStart (strong (str "Q:") <> str " ") <$> getBlocks e "answer" -> addToStart (strong (str "A:") <> str " ") <$> getBlocks e @@ -770,22 +771,22 @@ parseBlock (Elem e) = "variablelist" -> definitionList <$> deflistitems "figure" -> getFigure e "mediaobject" -> para <$> getMediaobject e - "caption" -> return mempty + "caption" -> skip "info" -> addMetadataFromElement e "articleinfo" -> addMetadataFromElement e - "sectioninfo" -> return mempty -- keywords & other metadata - "refsectioninfo" -> return mempty -- keywords & other metadata - "refsect1info" -> return mempty -- keywords & other metadata - "refsect2info" -> return mempty -- keywords & other metadata - "refsect3info" -> return mempty -- keywords & other metadata - "sect1info" -> return mempty -- keywords & other metadata - "sect2info" -> return mempty -- keywords & other metadata - "sect3info" -> return mempty -- keywords & other metadata - "sect4info" -> return mempty -- keywords & other metadata - "sect5info" -> return mempty -- keywords & other metadata - "chapterinfo" -> return mempty -- keywords & other metadata - "glossaryinfo" -> return mempty -- keywords & other metadata - "appendixinfo" -> return mempty -- keywords & other metadata + "sectioninfo" -> skip -- keywords & other metadata + "refsectioninfo" -> skip -- keywords & other metadata + "refsect1info" -> skip -- keywords & other metadata + "refsect2info" -> skip -- keywords & other metadata + "refsect3info" -> skip -- keywords & other metadata + "sect1info" -> skip -- keywords & other metadata + "sect2info" -> skip -- keywords & other metadata + "sect3info" -> skip -- keywords & other metadata + "sect4info" -> skip -- keywords & other metadata + "sect5info" -> skip -- keywords & other metadata + "chapterinfo" -> skip -- keywords & other metadata + "glossaryinfo" -> skip -- keywords & other metadata + "appendixinfo" -> skip -- keywords & other metadata "bookinfo" -> addMetadataFromElement e "article" -> modify (\st -> st{ dbBook = False }) >> addMetadataFromElement e >> getBlocks e @@ -802,8 +803,12 @@ parseBlock (Elem e) = "?xml" -> return mempty "title" -> return mempty -- handled in parent element "subtitle" -> return mempty -- handled in parent element - _ -> getBlocks e - where parseMixed container conts = do + _ -> skip >> getBlocks e + where skip = do + lift $ report $ IgnoredElement $ qName (elName e) + return mempty + + parseMixed container conts = do let (ils,rest) = break isBlockElement conts ils' <- (trimInlines . mconcat) <$> mapM parseInline ils let p = if ils' == mempty then mempty else container ils' @@ -1000,13 +1005,17 @@ parseInline (Elem e) = "footnote" -> (note . mconcat) <$> mapM parseBlock (elContent e) "title" -> return mempty - "affiliation" -> return mempty + "affiliation" -> skip -- Note: this isn't a real docbook tag; it's what we convert -- <?asciidor-br?> to in handleInstructions, above. A kludge to -- work around xml-light's inability to parse an instruction. "br" -> return linebreak - _ -> innerInlines - where innerInlines = (trimInlines . mconcat) <$> + _ -> skip >> innerInlines + where skip = do + lift $ report $ IgnoredElement $ qName (elName e) + return mempty + + innerInlines = (trimInlines . mconcat) <$> mapM parseInline (elContent e) codeWithLang = do let classes' = case attrValue "language" e of |